Skip to content

Commit

Permalink
Results from self hosted Github actions - NVIDIARTX4090
Browse files Browse the repository at this point in the history
  • Loading branch information
@arjunsuresh
arjunsuresh committed Feb 7, 2025
1 parent b7b24cc commit 3528411
Show file tree
Hide file tree
Showing 15 changed files with 538 additions and 536 deletions.
6 changes: 3 additions & 3 deletions .../measurements/arjun_spr-reference-gpu-pytorch_v2.6.0-scc24-base_cu124/README.md
View file
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
| Model | Scenario | Accuracy | Throughput | Latency (in ms) |
|---------------------|------------|------------|--------------|-------------------|
| stable-diffusion-xl | offline | () | 0.385 | - |
| Model | Scenario | Accuracy | Throughput | Latency (in ms) |
|---------------------|------------|----------------------|--------------|-------------------|
| stable-diffusion-xl | offline | (16.3689, 237.82579) | 0.384 | - |
6 changes: 4 additions & 2 deletions ...rence-gpu-pytorch_v2.6.0-scc24-base_cu124/stable-diffusion-xl/offline/README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ pip install -U mlcflow

mlc rm cache -f

mlc pull repo mlcommons@mlperf-automations --checkout=4c7402d8d52067a51229c79fa605b7ba6032c10f
mlc pull repo mlcommons@mlperf-automations --checkout=dce8947b93ecaa1e9d3fea463b8e67d91657ec88


```
Expand All @@ -37,6 +37,8 @@ Platform: arjun_spr-reference-gpu-pytorch_v2.6.0-scc24-base_cu124
Model Precision: fp32

### Accuracy Results
`CLIP_SCORE`: `16.3689`, Required accuracy for closed division `>= 31.68632` and `<= 31.81332`
`FID_SCORE`: `237.82579`, Required accuracy for closed division `>= 23.01086` and `<= 23.95008`

### Performance Results
`Samples per second`: `0.384774`
`Samples per second`: `0.384449`
116 changes: 58 additions & 58 deletions ...ence-gpu-pytorch_v2.6.0-scc24-base_cu124/stable-diffusion-xl/offline/accuracy_console.out
View file

Large diffs are not rendered by default.

50 changes: 25 additions & 25 deletions ...pr-reference-gpu-pytorch_v2.6.0-scc24-base_cu124/stable-diffusion-xl/offline/mlc-deps.mmd
View file
Original file line number Diff line number Diff line change
Expand Up @@ -23,52 +23,52 @@ graph TD
get-generic-python-lib,94b62a682bc44791_(_package.numpy_) --> get,generic-python-lib,_pip
get-cuda-devices,7a3ede4d3558427a_(_with-pycuda_) --> get,generic-python-lib,_package.numpy
app-mlperf-inference,d775cac873ee4231_(_reference,_sdxl,_pytorch,_cuda,_test,_r4.1-dev_default,_float16,_offline_) --> get,cuda-devices,_with-pycuda
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> detect,os
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> detect,os
detect-cpu,586c8a43320142f7 --> detect,os
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> detect,cpu
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,sys-utils-cm
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,python
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,cuda,_cudnn
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> detect,cpu
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,sys-utils-cm
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,python
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,cuda,_cudnn
get-generic-python-lib,94b62a682bc44791_(_torch_cuda_) --> get,python3
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,generic-python-lib,_torch_cuda
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,generic-python-lib,_torch_cuda
get-generic-python-lib,94b62a682bc44791_(_torchvision_cuda_) --> get,python3
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,generic-python-lib,_torchvision_cuda
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,ml-model,stable-diffusion,text-to-image,sdxl,raw,_pytorch,_fp16
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,dataset,coco2014,_validation,_with-sample-ids,_size.50
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,generic-python-lib,_torchvision_cuda
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,ml-model,stable-diffusion,text-to-image,sdxl,raw,_pytorch,_fp16
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,dataset,coco2014,_validation,_size.50,_with-sample-ids
generate-mlperf-inference-user-conf,3af4475745964b93 --> detect,os
detect-cpu,586c8a43320142f7 --> detect,os
generate-mlperf-inference-user-conf,3af4475745964b93 --> detect,cpu
generate-mlperf-inference-user-conf,3af4475745964b93 --> get,python
generate-mlperf-inference-user-conf,3af4475745964b93 --> get,mlcommons,inference,src
get-mlperf-inference-sut-configs,c2fbf72009e2445b --> get,cache,dir,_name.mlperf-inference-sut-configs
generate-mlperf-inference-user-conf,3af4475745964b93 --> get,sut,configs
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> generate,user-conf,mlperf,inference
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,loadgen
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,mlcommons,inference,src
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,mlcommons,inference,src
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> generate,user-conf,mlperf,inference
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,loadgen
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,mlcommons,inference,src
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,mlcommons,inference,src
get-generic-python-lib,94b62a682bc44791_(_package.psutil_) --> get,python3
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,generic-python-lib,_package.psutil
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,generic-python-lib,_package.psutil
get-generic-python-lib,94b62a682bc44791_(_package.diffusers_) --> get,python3
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,generic-python-lib,_package.diffusers
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,generic-python-lib,_package.diffusers
get-generic-python-lib,94b62a682bc44791_(_package.transformers_) --> get,python3
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,generic-python-lib,_package.transformers
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,generic-python-lib,_package.transformers
get-generic-python-lib,94b62a682bc44791_(_package.torchvision_) --> get,python3
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,generic-python-lib,_package.torchvision
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,generic-python-lib,_package.torchvision
get-generic-python-lib,94b62a682bc44791_(_package.accelerate_) --> get,python3
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,generic-python-lib,_package.accelerate
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,generic-python-lib,_package.accelerate
get-generic-python-lib,94b62a682bc44791_(_package.torchmetrics_) --> get,python3
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,generic-python-lib,_package.torchmetrics
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,generic-python-lib,_package.torchmetrics
get-generic-python-lib,94b62a682bc44791_(_package.torch-fidelity_) --> get,python3
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,generic-python-lib,_package.torch-fidelity
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,generic-python-lib,_package.torch-fidelity
get-generic-python-lib,94b62a682bc44791_(_package.open_clip_torch_) --> get,python3
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,generic-python-lib,_package.open_clip_torch
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,generic-python-lib,_package.open_clip_torch
get-generic-python-lib,94b62a682bc44791_(_package.opencv-python_) --> get,python3
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,generic-python-lib,_package.opencv-python
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,generic-python-lib,_package.opencv-python
get-generic-python-lib,94b62a682bc44791_(_package.scipy_) --> get,python3
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,generic-python-lib,_package.scipy
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,generic-python-lib,_package.scipy
get-generic-python-lib,94b62a682bc44791_(_package.pandas_) --> get,python3
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> get,generic-python-lib,_package.pandas
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> get,generic-python-lib,_package.pandas
detect-cpu,586c8a43320142f7 --> detect,os
benchmark-program,19f369ef47084895 --> detect,cpu
benchmark-program-mlperf,cfff0132a8aa4018 --> benchmark-program,program
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_sdxl,_cuda,_pytorch,_offline,_float16_) --> benchmark-mlperf
app-mlperf-inference-mlcommons-python,ff149e9781fc4b65_(_cuda,_pytorch,_sdxl,_offline,_float16_) --> benchmark-mlperf
Binary file modified ...ce-gpu-pytorch_v2.6.0-scc24-base_cu124/stable-diffusion-xl/offline/mlc-deps.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading

0 comments on commit 3528411

Please sign in to comment.